偏见缓解论文趋势 2023–2026

主要结论

• 偏见缓解论文从 2023 年的 50 篇增长到 2026 年的 76 篇，三年间扩大到约 1.5 倍。
• ICLR 是发偏见缓解论文最多的会议，2023–2026 年共 85 篇，占四个会议总量的 30%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 15 篇。
• 在「因果与公平」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的因果发现是 2.4 倍，偏见缓解是 1.5 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026Controlling for Omitted Variable Bias in Deep Neural Networks
• ICML 2026BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation
• ICLR 2026Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts
• CVPR 2026BAMI Training-Free Bias Mitigation in GUI Grounding
• NeurIPS 2025Any Large Language Model Can Be a Reliable Judge: Debiasing with a Reasoning-based Bias Detector
• ICML 2025Clipped SGD Algorithms for Performative Prediction: Tight Bounds for Stochastic Bias and Remedies
• ICLR 2025ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition
• CVPR 2025Data Distributional Properties As Inductive Bias for Systematic Generalization
• NeurIPS 2024Bayesian Identification of the Hamiltonian Inductive Bias in Dynamical Systems
• ICML 2024Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks
• ICLR 2024A 2-Dimensional State Space Layer for Spatial Inductive Bias
• CVPR 2024Diffeomorphic Template Registration for Atmospheric Turbulence Mitigation
• NeurIPS 2023Fast Model DeBias with Machine Unlearning
• ICML 2023FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction
• ICLR 2023Bias Propagation in Federated Learning
• CVPR 2023Bias Mimicking: A Simple Sampling Approach for Bias Mitigation
• NeurIPS 2026Empirical Bayes Rebiasing
• ICML 2026DISCO: Mitigating Bias in Deep Learning with Conditional Distance Correlation
• ICLR 2026BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses
• CVPR 2026Bias at the End of the Score

全部偏见缓解论文

共 85 篇，第 2 / 2 页

51. NeurIPS 2025Auto-Search and Refinement: An Automated Framework for Gender Bias Mitigation in Large Language Models
52. NeurIPS 2025Benford’s Curse: Tracing Digit Bias to Numerical Hallucination in LLMs
53. NeurIPS 2025Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language Models
54. NeurIPS 2025Diffusing DeBias: Synthetic Bias Amplification for Model Debiasing
55. NeurIPS 2025Disentangled Representation Learning via Modular Compositional Bias
56. NeurIPS 2025FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models
57. NeurIPS 2025FairNet: Dynamic Fairness Correction without Performance Loss via Contrastive Conditional LoRA
58. NeurIPS 2025FlashBias: Fast Computation of Attention with Bias
59. NeurIPS 2025Fourier Clouds: Fast Bias Correction for Imbalanced Semi-Supervised Learning
60. NeurIPS 2025How Does Topology Bias Distort Message Passing in Graph Recommender? A Dirichlet Energy Perspective
61. NeurIPS 2025How Memory in Optimization Algorithms Implicitly Modifies the Loss
62. NeurIPS 2025Implicit Bias of Spectral Descent and Muon on Multiclass Separable Data
63. NeurIPS 2025Improving Diffusion-based Inverse Algorithms under Few-Step Constraint via Linear Extrapolation
64. NeurIPS 2025Intervene-All-Paths: Unified Mitigation of LVLM Hallucinations across Alignment Formats
65. NeurIPS 2025Language‑Bias‑Resilient Visual Question Answering via Adaptive Multi‑Margin Collaborative Debiasing
66. NeurIPS 2025Learning to cluster neuronal function
67. NeurIPS 2025LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text Encoders
68. NeurIPS 2025Meta Guidance: Incorporating Inductive Biases into Deep Time Series Imputers
69. NeurIPS 2025More of the Same: Persistent Representational Harms Under Increased Representation
70. NeurIPS 2025Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data
71. NeurIPS 2025Obliviator Reveals the Cost of Nonlinear Guardedness in Concept Erasure
72. NeurIPS 2025On Inductive Biases That Enable Generalization in Diffusion Transformers
73. NeurIPS 2025On the Bias of Next-Token Predictors Toward Systematically Inefficient Reasoning: A Shortest-Path Case Study
74. NeurIPS 2025Position: If Innovation in AI systematically Violates Fundamental Rights, Is It Innovation at All?
75. NeurIPS 2025Rectifying Soft-Label Entangled Bias in Long-Tailed Dataset Distillation
76. NeurIPS 2025Robust Graph Condensation via Classification Complexity Mitigation
77. NeurIPS 2025Silencer: From Discovery to Mitigation of Self-Bias in LLM-as-Benchmark-Generator
78. NeurIPS 2025Tackling Biased Evaluators in Dueling Bandits
79. NeurIPS 2025The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels
80. NeurIPS 2025The Persistence of Neural Collapse Despite Low-Rank Bias
81. NeurIPS 2025Training the Untrainable: Introducing Inductive Bias via Representational Alignment
82. NeurIPS 2025TranSUN: A Preemptive Paradigm to Eradicate Retransformation Bias Intrinsically from Regression Models in Recommender Systems
83. NeurIPS 2025Uncovering the Spectral Bias in Diagonal State Space Models
84. NeurIPS 2025Unveiling Extraneous Sampling Bias with Data Missing-Not-At-Random
85. NeurIPS 2025When majority rules, minority loses: bias amplification of gradient descent

常见问题

2023–2026 年四大会议一共有多少篇偏见缓解论文？

共 284 篇，按年份分别是 2023 年 50 篇、2024 年 73 篇、2025 年 85 篇、2026 年 76 篇。

NeurIPS 2026 有多少篇偏见缓解论文？

NeurIPS 2026 有 14 篇偏见缓解论文，上一届是 38 篇。

ICLR 2026 有多少篇偏见缓解论文？

ICLR 2026 有 24 篇偏见缓解论文，上一届是 23 篇。

ICML 2026 有多少篇偏见缓解论文？

ICML 2026 有 24 篇偏见缓解论文，上一届是 17 篇。

CVPR 2026 有多少篇偏见缓解论文？

CVPR 2026 有 14 篇偏见缓解论文，上一届是 7 篇。

哪个会议的偏见缓解论文最多？

ICLR，2023–2026 年共 85 篇。